Category: Data Analytics

Purpose

In the business world, prompting is not guessing the magic words. Its writing a clear work order for an AI tool, testing it, and iterating until outputs are reliable. In this lab you will:

• define a business problem with a small sample dataset,
• build a reusable Prompt Pack (prompt templates),
• run a Prompt Clinic (before/after improvement).

Allowed tools

You may use ChatGPT, Gemini, or Microsoft Copilot to run your prompts. You may also use Excel/Google Sheets for quick calculations.

• You must disclose any AI use in the AI Use Note section of the template.
• **Do not paste sensitive data** (PII, passwords, non-public company data). Use de-identified, public, or synthetic data.

What you submit

Submit **one completed Word document**:

• **CAI3801_Week03_Lab02_your_name.docx** (download by clicking the downward arrow) –

Step 1 Choose your problem + sample data (required)

Pick ONE of these options:

Option A (recommended): Use a Starter Case (provided in the template doc – starter case #1-4).

Choose one starter case and use the included mini-dataset.

Option B: Create your own business problem (creative option- starter case #5).

Your problem must include:

1) a clear **goal** (what success means),

2) **constraints** (at least 2),

3) **sample data** you can paste into an AI tool (minimum **5 rows** **4 columns** or equivalent text records).

**Important:** Your data can be small and synthetic. The key is that its realistic and supports your prompts.

Step 2 Prompt Pack (3 required + 2 optional)

In the template, complete **Prompt 13 (required)**:

• each prompt must be reusable (a teammate could reuse it) – but different from each other,
• include RTC-CO (Role, Task, Context, Constraints, Output format),
• include a structured output format (table, bullets with headings, JSON-like schema, etc.),
• version your prompts (v1, v2).
• run them in your chosen AI tool.

**Prompt 45 are optional** (extra practice; not required for grading unless you want to show more work and get extra credit).

Step 3 Prompt Clinic (before/after)

Pick **ONE** of your prompts (from Prompt 13) and do a before/after improvement:

1) Run a **baseline** version save a short excerpt of output.

2) Score it using the rubric (02 each: Relevance, Constraints, Actionability, Structure, Self-check).

3) Rewrite the prompt using RTC-CO + quality checks run again.

4) Re-score and briefly explain what improved.

Step 4:

Reflection (35 sentences/bullets): What did you learn? What broke on the worst case or what worked for the best case? What would you change next?

Grading (100 points + 10 extra credit)

• Problem definition + sample data quality: 20
• Prompt Pack (3 required prompts): 25
• Prompt Clinic (before/after + rubric scoring): 30
• Creativity (Use of different techniques learned from class lecture + defining your own business problem + actionable recommendations etc.): 15
• Professional practice (AI Use Note + clarity/formatting): 10
• Extra credit (2 optional prompts): 10

Tips for success

• Keep prompts **specific** (use the data you have, not generic advice).
• Use **constraints** (length, tone, do/dont, budget limits, CPA cap, etc.).
• Ask for a **structured output** (tables beat paragraphs for business work).
• Include a **self-check** step (flag assumptions + what to verify).

Academic integrity

This lab teaches responsible AI use. Using an AI tool is allowed (and expected), but you must:

• write your own scenario/data (or use the starter case),
• show your prompt versions and your scoring,
• submit your work in your own words.

(Your submission should reflect your thinking and decisions, not just raw AI output.)

Data Analytics in Hospitality kindly fill the formulas added and the attached outline for the project

For this week’s discussion, you will discuss the following:

1. What are the four questions that you need to ask before designing a dashboard.
2. Why is it important to ask these questions?
3. What would happen if you did not ask these questions?

EXAMPLE POST:

As an Architect with more than 14 years of experience in project management in the construction business, I have learned that a dashboard is only as effective as the questions asked before it is designed. Based on this weeks learning, there are four key questions that should always be addressed prior to building a dashboard.

The first question is: Who is the audience?
Understanding whether the dashboard is intended for executives, project managers, or operational teams is critical. Each group requires a different level of detail, frequency, and type of insight. For example, executives typically focus on KPIs and trends, while project managers need operational and task-level metrics.

The second question is: What decisions will be made using this dashboard?
Dashboards should be decision-driven, not data-driven. Clarifying the decisions ensures that the dashboard provides actionable insights rather than overwhelming users with unnecessary data.

The third question is: What metrics and data sources are required?
Identifying the right KPIs and ensuring data accuracy, relevance, and reliability is essential. In construction, using incorrect or inconsistent data can lead to flawed cost forecasts, scheduling errors, or resource misallocation.

The fourth question is: How often will the dashboard be used and updated?
The update frequency must align with the business process. Real-time dashboards may be necessary for operations, while weekly or monthly updates may be sufficient for strategic reviews.

It is important to ask these questions because they ensure alignment between business objectives, users needs, and data integrity. A well-designed dashboard supports clarity, efficiency, and confident decision-making.

If these questions are not asked, dashboards often become cluttered, confusing, and underutilized. They may present irrelevant metrics, mislead decision-makers, or fail to support timely actionsultimately reducing trust in data and analytics.

In summary, asking these four questions upfront transforms dashboards from simple visual reports into powerful decision-support tools that add real value to the organization.

I need a 4-5 page case study comparison report that makes a micro-level comparison of two luxury fashion houses: Hermes and Burberry. The report should focus on how each brand uses data to support market positioning, production and supply discipline, brand identity preservation, sustainability initiatives, and pricing/client relationship strategies. If you could compare the types of data and sources the brands use, whether they are customer, operational, or financial. Then, analyze how data informs their decision-making frameworks and business models, and then evaluate the effectiveness and limitations of each approach using measurable and/or observable outcomes. Finally, finish the report with evidence based reccomendations to strengthen or refine their data-driven practices. Do not worry about the presentation portion or the reflection, simply the 4-5 report that is the bulk of the assignment. If you can provide sources and cite them at the end of the report in MLA as well, that would be greatly appreciated. Please let me know if you have any questions or concerns.

Required information

[The following information applies to the questions displayed below.]

Keywords: Customer Profitability, Inventory Management, Customer Relationship Management

Decision-Making Context: Merchandising companies sell products to customers. They make money by selling the products for more than what they paid. In this lab, we compute the gross margin for each product to identify the companys most profitable products. This analysis allows merchandising companies to focus their efforts on selling the most profitable products, which in turn helps them make more profits.

Required:

1. Create calculated fields for the gross margin and gross margin percentage.
2. Create a histogram to visualize the distribution of gross margin percentage across SKUs.
3. Adjust the automated bin size to 0.025.
4. Create a list of SKUs in the highest bin.

Data:

Specify the Question: Which products (SKUs) are the most profitable to sell?

Obtain the Data: Fancy Fruits is a fictitious mail-order business that sells exotic fruit from around the world to customers throughout the United States. The company keeps a price list for each product. We will work from this price list to find the items that are most profitable per dollar of sales.

Analyze the Data: Refer to lab 1.3 in your text for additional instructions and steps.

Upload one Word or PDF document containing all of your screenshots for this Lab using the button below.

Note: Please submit your file attachment response in one of the approved file formats; Word file (.doc or .docx), Excel file (.xls or .xlsx), or PDF. To submit photo or image files please paste them into Word or PDF. Consult with your instructor as needed on their preferred file attachment format.

1. Take a screenshot of your histogram, paste it into a Word document named Lab 1.3 Tableau Submission.docx, and label the screenshot Submission 1.
2. Take a screenshot of your dashboard, paste it into the same Word document, and label the screenshot Submission 2.

see the video and do the same

I am still a beginner in power b.i so please dont make it look advanced at all
Complete the project to practice both using Power BI and analyzing data.

Save all changes described in the project and make three to five of your own changes that enhance data analysis. Strive to make changes that are more significant than the changes you made in the previous project.

Submit a Word document report of fewer than eight pages with the following level one headings and content. Use level two and three headings as needed.

• Introduction
• Changes
  • Describe the changes you made and why you made each change.
  • Insert figures (screenshots of your changes). Ensure these are properly labeled per APA 7.
• Analysis
  • Describe insights gleaned from your data analysis.
  • Insert figures (screenshots of visualizations from Power BI).
• Conclusion

Requirements

• Submit only one Word document.
• APA version 7 format for the report.
  • Include a cover page and abstract
  • Do not include a table of contents
  • Use for guidance.
• Review the rubric to ensure you understand how you will be assessed.

hi can you solve this now please. the professor didn’t give me any other information so u can start.

Complete Decision Trees for data mining and present your data mining process using Jupyter Notebook. The codes used in this assignment need to work and be explained. Format your Jupyter notebook to make it appropriate for your presentation. Using the data provided, create a Decision Trees model. Use Python computer programming to build the Decision Trees model. The steps you are following to create the Decision Trees model should include:

Data: Use data decisiontree_Data (See the attached)

1. Import the data files into new data frames.
2. Create the predictors
3. Creating the target variable
4. Obtaining the data set for decision trees
5. Splitting the data into training and testing data sets
6. Decision Trees for Classification using the DecisionTreeClassifier
7. Visualize Decision Trees for Classification
8. Make a forecast/prediction
9. Performance analysis
10. Discuss as a group your decision tree findings and recommendations for use. Summarize your group discussion, including where team members may have disagreed.
11. Discuss as a group how decision tree tools can be used by different organizations and how valuable each team member found this tool to be. Conclude with a summary of this group discussion in your presentation, including where team members may have disagreed.

Purpose

In this assignment, you will develop essential data analysis skills by working with survey data in Excel. Businesses frequently use surveys to collect insights from employees and customers to better understand attitudes, behaviors, and decision-making patterns. By analyzing survey data, organizations can identify trends, evaluate relationships between key factors, and make informed business decisions.

Descriptive analytics plays a crucial role in this process by summarizing data, uncovering patterns, and providing a foundation for strategic recommendations. This assignment emphasizes the practical application of data analysis by having you interpret a real-world dataset, extract meaningful insights, and assess relationships between key variables. Your goal is to analyze and organize the data to present a clear and actionable business case for stakeholders.

Task

You are a data analyst at a consulting firm specializing in eCommerce solutions for manufacturing. Your firm recently conducted a survey of middle managers in manufacturing firms to assess their attitudes toward online distribution channels and third-party digital platforms.

Your analysis should focus on understanding key trends, identifying factors influencing digital adoption, and generating insights that inform business decisions. The final report will be presented to executives, data analysts, and strategy teams, requiring you to translate data insights into meaningful business recommendations.

Your task includes:

• Summarizing survey responses using descriptive statistics
• Evaluating relationships between key variables
• Exploring demographic differences in attitudes toward digital adoption
• Providing strategic recommendations based on findings

Understanding the Business Challenge

Many manufacturing firms are navigating challenges in adopting eCommerce strategies. Your analysis should address::

• How do manages perceive online distribution channels?
• What are the key concerns regarding third-party platforms (e.g., Amazon, Alibaba)?
• Does confidence in internal digital skills influence investment in eCommerce?

Your findings will help your consulting firm develop data-driven strategies for improving digital adoption in manufacturing.

Key Concepts

• Manufacturing Firm A company that produces physical goods by transforming raw materials into finished products using industrial processes, machinery, and labor.
• Digital Adoption in Manufacturing How manufacturing firms integrate digital tools and technologies to enhance operations and expand online sales.
• Online Distribution Channels Digital sales channels that allow businesses to sell products directly to customers through their own eCommerce platforms, websites, or digital storefronts. Example: A manufacturer selling through its own website (e.g., Shopify, Square) or using a direct-to-consumer (DTC) model (e.g., Nike selling through Nike.com instead of Amazon).
• Third-Party Digital Platforms External marketplaces where businesses list and sell products without owning the platform. These platforms expand customer reach but come with fees and platform restrictions. Example: Amazon, Alibaba, eBay, Walmart Marketplace, Etsy.
• eCommerce Strategies Approaches businesses use to sell products online, optimize marketing, logistics, and customer experience.
  • Direct-to-Consumer (DTC): Selling products through a companys own website (e.g., Allbirds, Warby Parker).
  • Omnichannel Retailing: Integrating physical stores, websites, and third-party platforms (e.g., H&M selling in stores and online).
  • Marketplace Strategy: Using third-party platforms (e.g., Amazon, Alibaba) to expand reach.
  • Subscription eCommerce: Offering recurring product deliveries (e.g., Dollar Shave Club, Birchbox).

Understanding the Dataset

The dataset includes survey responses from 263 middle managers working in manufacturing firms. Respondents were selected based on the following criteria:

• Employed in a manufacturing company
• Hold a managerial position (at least middle management level)
• Supervise at least two subordinates
• Fluent in English
• Confirmed that their company markets products through online distribution channels

The survey consists of four key categories, each measured on a 17 scale (1 = Strongly Disagree, 7 = Strongly Agree).

Survey Categories

• Investment in Online Distribution Channels (INT14): Perceived benefits of online distribution for international market expansion, cost reduction, and operational improvements.
• Satisfaction with the Companys eCommerce Platform (CMS13): Evaluates the perception of a companys own eCommerce platform as a viable sales channel.
• Perceptions of Third-Party Marketplace Platforms (TPMP13): Measures how businesses view third-party platforms (Amazon, Alibaba) as potential sales growth opportunities.
• Confidence in Internal Digital Capabilities (COM14): Examines how confident companies are in their internal skills, training, and discussions regarding eCommerce.

Additional Variables

The dataset also includes demographic and organizational characteristics that may influence survey responses:

Variable	Description
Company Size	SME (0) vs. Large Company (1)
Gender	Female (0) vs. Male (1)
Industry	Textile, Electronics, Fast Moving Consumer Goods (FMCG), Other
Work Territory	UK, USA, EU, Other non-EU
Age Groups	Categorized into five brackets
Seniority Levels	Middle Manager (1), Senior Manager (2), Top Executive/Board Member (3)

By analyzing these variables, you can identify trends and compare attitudes across different groups.

Dataset Analysis

For this assignment, you will analyze the to evaluate manufacturers eCommerce practices. Using Excel, conduct the following analysis and present your findings in a professional report.

1. Descriptive Statistics

Analyze attitudes toward eCommerce adoption by calculating key statistics:

• Central Tendency (Mean, Median, Mode)
  • Investment in online distribution (INT14)
  • eCommerce platform satisfaction (CMS13)
  • Third-party marketplace perception (TPMP13)
  • Confidence in internal skills (COM14)
• Variability (Standard Deviation, Range)
  • Do responses within each category show high agreement or variation?
• Categorical Breakdown
  • Company size, industry, and work territory distributions
  • Age group and seniority breakdown

2. Correlation Analysis

Use Excel’s built-in correlation function to examine relationships between key variables. Interpret correlations using the following scale:

Corelation Coefficient	Relationship Strength
0.00 – 0.20	Weak or No Relationship
0.21 – 0.40	Weak Relationship
0.41 – 0.60	Moderate Relationship
0.61 – 0.80	Strong Relationship
0.81 – 1.00	Very Strong Relationship

Analyze the following relationships and create scatterplots with trendlines to visualize key correlations.

• Investment in online distribution (INT14) vs. eCommerce platform satisfaction (CMS13)
• Investment in online distribution (INT14) vs. third-party platform perception (TPMP13)
• Confidence in internal skills (COM14) vs. investment, CMS, and TPMP scores

3. Demographic Comparisons

Use Pivot Tables to group responses by age and gender, and analyze:

• Average scores for INT14, CMS13, and TPMP13
• Variations in digital adoption attitudes across age groups and gender
• Bar charts to compare attitudes across different groups

4. Visualizing Key Insights

Use Excel charts to present findings:

• Bar Chart: Compare attitudes by industry, company size, or seniority level
• Scatter Plot: Show relationships between investment in online distribution and eCommerce satisfaction
• Box Plot or Histogram: Analyze variations in confidence in internal digital capabilities

5. Strategic Recommendations

Based on your findings, provide three strategic recommendations for improving digital adoption in manufacturing.

• How should manufacturing firms approach eCommerce investment?
• What role do internal digital skills play in eCommerce adoption?
• Should companies focus more on third-party platforms or their own eCommerce platforms?

Your recommendations should be supported by insights from descriptive statistics and correlation analysis.

Submission

• Submit two documents, a Microsoft Word written analysis with data visualizations and a Microsoft Excel workbook file.
• Write from the perspective of a data analyst, providing actionable insights for business decision-makers.
• Ensure originality, demonstrating your ability to interpret data and develop strategic recommendations.
• Use proper APA citations for any industry reports, academic research, or business frameworks referenced.
• Formatting: 12-point Times New Roman or 11-point Arial, 1-inch margins, and double-spacing.
• Include tables and graphs, properly labeled in APA format.